Automotive industry faces challenges in manufacturing like increasingly individualized products with a short lead-time to market and higher quality. Additionally to that, new technologies, such as Internet of Things (IoT), big data, data analytics and cloud computing, are changing the production into the next generation of industry. To address these challenges intelligent manufacturing in combination with data analytics plays an important role. In this sense, the integration of prescriptive analytics in manufacturing may help industry to increase productiveness. This paper provides first a comprehensive review of key elements for prescriptive analytics in manufacturing. Furthermore, this paper highlights requirements for a prescriptive analytics based production control, so called prescriptive automation, and finally points out field of activities in this topic.

The paper examines the development of production systems from automated to data analysis-supported process control. In current concepts, process optimization is carried out by data analysis with the help of a decision support system after the production process. Prescriptive automation envisages controlling the process before and autonomously on the basis of a prescriptive analytics model. The development of an IT architecture is identified as an essential part of the overall concept. On the basis of expert interviews and current literature reviews, the question is answered, which requirements an IT architecture for prescriptive automation has to fulfill. These requirements are opposed to solution components with the goal of a modular architectural concept. On basis of the requirements and therefore needed solution components, a reference architecture is identified on the assumption of the data processing resources. The main processing components of this architecture are a combination of edge and cloud computing.